Sensor harvests energy in ADAS wheels

Power generation and sensing are combined in the InWheelSense energy harvesting and sensing module for automotive wheels in advanced driver assistance system (ADAS) applications.

The InWheelSense module attaches to the wheel of a vehicle and converts the force of tyre rotation into piezoelectric power and generates battery-less sensing and data collection and transmission from the wheel. According to TDK, delivering an electrical source in this hostile environment is conventionally difficult. The module enables sensing of road surface conditions, wheel alignment, tyre pressure and other conditions in real-time. Smart mobility applications can be implemented when it connects to the roadside infrastructure to help empower smart mobility. The sensors can connect with smart bridges, traffic controls and signage to communicate real-time data and support vehicle-to-pedestrian, vehicle-to-infrastructure and vehicle-to-vehicle networks.

Until now, environmental sensing for ADAS features have largely been driven by perception sensors like lidar and radar, image and infra red cameras. These sensors provide valuable data for ADAS operations but for improved sensing performance during adverse weather or all terrain conditions, non-perception sensors (such as piezo, inertial measurement unit (IMU), ultrasound, and strain gauges) embedded in the tyre or wheel can more accurately digitalise and classify driving and road conditions.

The InWheelSense energy harvesting module uses piezoelectric elements to generate electric power from mechanical motion or force. By placing the device at the boundary between the tyre and the wheel, the module generates electricity using the force received from the road surface as the tyre rotates. It enables scalable power generation according to the load of the driving system by allowing multiple device connections along the wheel’s circumference. It achieves an average continuous power output of 1mW when driving at 65mph / 105km/h. This perpetual source of power is particularly suitable for digitalising driving, road and tyre conditions using a range of non-perception-based sensing, TDK says.

A vehicle’s speed, turning and other changes in operating conditions can cause variations in the electromotive force characteristics of the device. The InWheelSense module can sense various driving conditions using those power changes through analysis of the waveforms from the piezoelectric effect. Waveforms are output when the tyres contact the road surface, so they are continuously generated as the car drives. As the speed increases, the frequency of the waveforms also increases, and when the direction of travel changes, the load on the tyres will change, creating different waveforms that reflect the driving characteristics at that time. A waveform is delivered for each wheel revolution, therefore the InWheelSense module is able to detect not only the speed during driving, but also road surface conditions based on the shape of the output waveform. The different waveforms reflect the driving characteristics at that time.

InWheelSense also allows for real-time collection of data from additional wheel sensors (including accelerometers, barometric pressure and temperature) to the onboard computation unit. This control module platform includes power management, digital compute capacity and low power data transmission using Bluetooth Low Energy. Data can be stored and / or processed through an inference engine in the control module, powered by an edge processor that enables algorithms to make meaningful inferences on the fly. This allows lower-latency control responses without dependency on the cloud during adverse weather conditions. All the power needed to support the data collection, processing, and action (transmission) is supplied by the energy harvesting power generator, confirms TDK.

InWheelSense provides an evaluation kit dedicated for conducting simple evaluations of the energy-harvesting module as a sample that can be attached to existing wheels. This kit enables wireless collection of data outputted from the device and power generation performance without the need for additional equipment.

https://www.tdk.com

> Read More

Face recognition package increases accuracy

Image sensing libraries used in the OKAO Vision face recognition package by Omron Electronic Components Europe are claimed to provide “highly accurate” deep learning face recognition. Developers can deploy OKAO Vision on their choice of embedded hardware platform.

The deep learning libraries of OKAO Vision Face Recognition V9.0 address applications that require accuracy under various conditions including poor lighting and when the face is at various angles relative to the detector. These include security and access control, time and attendance monitoring, login/wake up systems, and camera auto focus/auto-exposure control.

The platform can be used to monitor attendance at face to face and online meetings, which will facilitate contact tracing and verification of attendance. Another application will be in automotive design, for example in driver recognition to manage features such as seat adjustment.

The face recognition libraries achieve “excellent” evaluation results with various skin tones and face sizes, says Omron. It delivers a low error rate down to image size as small as 40 pixels. Benchmark testing with Intel and Arm processors has demonstrated that OKAO Vision Face Recognition V9.0 maintains exceptionally fast recognition times despite the enhanced accuracy, reports Omron. This ensures that users in access control applications for example will be barely conscious of the need to wait for validation of their identity.

The complete OKAO Vision Face Recognition V9.0 package contains modular libraries that provide sensing capabilities including expression estimation, age and gender estimation, and photographic image beautification including red eye reduction, facial shaping, eye enlargement, and blemish removal. Users can combine various modules’ functionalities to add value to applications.

OKAO Vision is available as a set of software libraries and can integrate with Linux, Windows and iOS operating systems. Users can leverage Omron’s machine vision package in embedded systems running on custom hardware. Off-the-shelf libraries are already available for various platforms, adds Omron.

http://components.omron.eu

> Read More

Glucose measuring wristband means non-stop monitoring

At this year’s CES, Quantum Operation will showcase what it claims is the world’s first glucose measuring wristband which enables non-stop monitoring.

The Tokyo-based healthcare IoT start-up explains that the non-invasive glucose monitor uses patented spectrum sensing technology which enables the monitoring sensor to accurately measure glucose in a person’s bloodstream through the skin while being worn around the wrist. The monitor eliminates the need for daily needle uses for diabetic patients, making it more convenient – and pain-free – for users.

The company will also highlight its oxygen saturation (SpO2) measuring sensor that can be worn around the wrist.

The non-invasive 24/7 monitoring relies on Quantum Operation’s core technologies that include spectrometer materials. One of which is designed to emit an optimal spectrum, and another that is highly responsive to target spectra. The wristbands also employ firmware that efficiently extracts targeted data by cancelling noise.

Quantum Operation explains that these technologies can be used to measure all types of vital signs, ranging from heart rate to electrocardiography (ECG). Patients’ conditions can be monitored remotely for convenience and enabling them to continue their normal daily activity as much as possible.

“Until now, sticking a need into your finger or arm has been the only available method for accurately measuring your glucose level,” said CEO Kazuma Kato. “Our wristband will change that, making the painful daily routine unnecessary for all diabetic patients.”

He added: “Our core technologies also enable healthcare businesses to compile accurate big data and provide better solutions for disease control and management. We are very excited to introduce these technologies at CES 2021.”

Quantum Operation is a Tokyo-based, healthcare IoT start up focused on making vital sign measurement as easy and painless as possible. It says its mission is to help people enjoy a healthier and longer lives. Its proprietary technologies are used to provide solutions for both patients and healthcare providers.

https://quantum-op.co.jp

> Read More

Intel RealSense ID processes images locally and encrypts for privacy

Privacy was a top priority in the design of the Intel RealSense ID facial authentication, explains the company at its launch.

Intel RealSense ID combines an active depth sensor with a specialised neural network designed to deliver secure, accurate and user-aware facial authentication. It was designed and built specifically for user protection and processes all facial images locally and encrypts all user data, explains the company.

Intel RealSense ID works with various access systems, including smart locks, access control, point of sale sites, ATMs and kiosks.

“Intel RealSense ID combines purpose-built hardware and software with a dedicated neural network designed to deliver a secure facial authentication platform that users can trust,” explained Sagi Ben Moshe, Intel corporate vice president and general manager of Emerging Growth and Incubation.

No network set up is required and enrolment is simple, says Intel, for accurate, natural facial authentication to simplify secure entry. Using only a glance, users are able to quickly unlock what’s important to them. Intel RealSense ID combines active depth with a specialised neural network, a dedicated SoC and embedded secure element to encrypt and process user data quickly and safely.

To ensure continued ease of use, Intel RealSense ID also adapts to users over time as they change physical features, such as facial hair and glasses. The system works in various lighting conditions for people with a wide range of heights or complexions, reassures Intel.

It has been developed because traditional authentication methods leave users vulnerable to ID theft and security breaches. Companies and individuals are turning to facial authentication technology to meet the highest levels of security and privacy.

Suitable for use in finance, healthcare and smart access control, Intel RealSense ID has built-in anti-spoofing technology to protect against false entry attempts using photographs, videos or masks. It also provides a one-in-1-million false acceptance rate.

To protect user’s privacy, Intel RealSense ID processes all facial images locally and encrypts all user data. It is also only activated through user awareness and will not authenticate unless prompted by a pre-registered user.

http://www.intel.com

> Read More

About Smart Cities

This news story is brought to you by smartcitieselectronics.com, the specialist site dedicated to delivering information about what’s new in the Smart City Electronics industry, with daily news updates, new products and industry news. To stay up-to-date, register to receive our weekly newsletters and keep yourself informed on the latest technology news and new products from around the globe. Simply click this link to register here: Smart Cities Registration